Machine learning-based estimation of CO2 footprint and environmental-mechanical performance of blended cement concrete

Blended cements with supplementary cementitious materials (SCMs) are extensively used to mitigate the environmental impact of concrete. However, assessing their environmental performance often requires detailed data and time-intensive analyses. This study presents a machine learning-based methodolog...

Full description

Saved in:
Bibliographic Details
Main Authors: Felipe Vargas, Iván La Fé-Perdomo, Jorge A. Ramos-Grez, Ivan Navarrete
Format: Article
Language:English
Published: Elsevier 2025-07-01
Series:Case Studies in Construction Materials
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S221450952500539X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850148413517070336
author Felipe Vargas
Iván La Fé-Perdomo
Jorge A. Ramos-Grez
Ivan Navarrete
author_facet Felipe Vargas
Iván La Fé-Perdomo
Jorge A. Ramos-Grez
Ivan Navarrete
author_sort Felipe Vargas
collection DOAJ
description Blended cements with supplementary cementitious materials (SCMs) are extensively used to mitigate the environmental impact of concrete. However, assessing their environmental performance often requires detailed data and time-intensive analyses. This study presents a machine learning-based methodology for the rapid estimation of the CO₂ footprint and environmental-mechanical performance (CO₂/MPa ratio) of concrete mixtures using only the proportions of their main components (i.e., ordinary portland cement (OPC), SCMs, aggregates, water, and water-reducing admixtures). The models were developed using a dataset of 246 mixtures compiled from the literature and validated against 15 experimentally tested mixtures. The results demonstrate that the Gaussian Process Regressor provides the highest predictive accuracy for both CO₂ footprint and CO₂/MPa ratio. Feature analysis revealed that OPC content has the highest impact on the CO₂ footprint, while aggregate fraction has the most significant influence on the CO₂/MPa ratio. An optimization framework was also implemented to explore the trade-offs among mix components, showing that increasing SCM content does not always lead to improved CO₂/MPa ratio, highlighting the need for balanced mixture design. The developed models offer a practical tool for supporting early-stage decision-making in construction projects by enabling rapid sustainability assessments of concrete mixtures, independent of specific SCM types, production methods, or geographical context.
format Article
id doaj-art-7a96347fbfae4c45bbd202dc2975fb18
institution OA Journals
issn 2214-5095
language English
publishDate 2025-07-01
publisher Elsevier
record_format Article
series Case Studies in Construction Materials
spelling doaj-art-7a96347fbfae4c45bbd202dc2975fb182025-08-20T02:27:15ZengElsevierCase Studies in Construction Materials2214-50952025-07-0122e0474110.1016/j.cscm.2025.e04741Machine learning-based estimation of CO2 footprint and environmental-mechanical performance of blended cement concreteFelipe Vargas0Iván La Fé-Perdomo1Jorge A. Ramos-Grez2Ivan Navarrete3Institute of Civil Engineering, Austral University of Chile, General Lagos 2086, Valdivia, ChileEscuela de Ingeniería Mecánica, Pontificia Universidad Católica de Valparaíso, Valparaíso 2340025, ChileDepartment of Mechanical and Metallurgical Engineering, School of Engineering, Pontificia Universidad Católica de Chile, Vicuña Mackenna 4860, Macul, Santiago, Chile; Research Center for Nanotechnology and Advanced Materials (CIEN-UC), Vicuña Mackenna 4860, Macul, Santiago, ChileDepartment of Construction Engineering and Management, School of Engineering, Pontificia Universidad Católica de Chile, Vicuña Mackenna 4860, Macul, Santiago, Chile; Concrete Innovation Hub UC (CIHUC), Pontificia Universidad Catolica de Chile, Vicuña Mackenna 4860, Macul, Santiago, Chile; Corresponding author at: Department of Construction Engineering and Management, School of Engineering, Pontificia Universidad Católica de Chile, Vicuña Mackenna 4860, Macul, Santiago, Chile.Blended cements with supplementary cementitious materials (SCMs) are extensively used to mitigate the environmental impact of concrete. However, assessing their environmental performance often requires detailed data and time-intensive analyses. This study presents a machine learning-based methodology for the rapid estimation of the CO₂ footprint and environmental-mechanical performance (CO₂/MPa ratio) of concrete mixtures using only the proportions of their main components (i.e., ordinary portland cement (OPC), SCMs, aggregates, water, and water-reducing admixtures). The models were developed using a dataset of 246 mixtures compiled from the literature and validated against 15 experimentally tested mixtures. The results demonstrate that the Gaussian Process Regressor provides the highest predictive accuracy for both CO₂ footprint and CO₂/MPa ratio. Feature analysis revealed that OPC content has the highest impact on the CO₂ footprint, while aggregate fraction has the most significant influence on the CO₂/MPa ratio. An optimization framework was also implemented to explore the trade-offs among mix components, showing that increasing SCM content does not always lead to improved CO₂/MPa ratio, highlighting the need for balanced mixture design. The developed models offer a practical tool for supporting early-stage decision-making in construction projects by enabling rapid sustainability assessments of concrete mixtures, independent of specific SCM types, production methods, or geographical context.http://www.sciencedirect.com/science/article/pii/S221450952500539XSupplementary Cementitious MaterialsGaussian Process RegressorPermutation Feature ImportanceNSGA-II
spellingShingle Felipe Vargas
Iván La Fé-Perdomo
Jorge A. Ramos-Grez
Ivan Navarrete
Machine learning-based estimation of CO2 footprint and environmental-mechanical performance of blended cement concrete
Case Studies in Construction Materials
Supplementary Cementitious Materials
Gaussian Process Regressor
Permutation Feature Importance
NSGA-II
title Machine learning-based estimation of CO2 footprint and environmental-mechanical performance of blended cement concrete
title_full Machine learning-based estimation of CO2 footprint and environmental-mechanical performance of blended cement concrete
title_fullStr Machine learning-based estimation of CO2 footprint and environmental-mechanical performance of blended cement concrete
title_full_unstemmed Machine learning-based estimation of CO2 footprint and environmental-mechanical performance of blended cement concrete
title_short Machine learning-based estimation of CO2 footprint and environmental-mechanical performance of blended cement concrete
title_sort machine learning based estimation of co2 footprint and environmental mechanical performance of blended cement concrete
topic Supplementary Cementitious Materials
Gaussian Process Regressor
Permutation Feature Importance
NSGA-II
url http://www.sciencedirect.com/science/article/pii/S221450952500539X
work_keys_str_mv AT felipevargas machinelearningbasedestimationofco2footprintandenvironmentalmechanicalperformanceofblendedcementconcrete
AT ivanlafeperdomo machinelearningbasedestimationofco2footprintandenvironmentalmechanicalperformanceofblendedcementconcrete
AT jorgearamosgrez machinelearningbasedestimationofco2footprintandenvironmentalmechanicalperformanceofblendedcementconcrete
AT ivannavarrete machinelearningbasedestimationofco2footprintandenvironmentalmechanicalperformanceofblendedcementconcrete